logitdyn

class quantecon.game_theory.logitdyn.LogitDynamics(data, beta=1.0)[source]

Class representing the logit-response dynamics model.

Parameters:

dataNormalFormGame or array_like: The game played in the logit-response dynamics model.
betascalar(float): The level of noise in player’s decision.

Attributes:

Nscalar(int): The number of players in the game.
playerslist(Player): The list consisting of all players with the given payoff matrix.
nums_actionstuple(int): Tuple of the number of actions, one for each player.
betascalar(float): See parameters.
player.logit_choice_cdfsarray_like(float): The choice probability of each actions given opponents’ actions.

Methods

`logit_choice_cdfs`()	Return the tuple of choice probabilities.
`play`([init_actions, player_ind_seq, ...])	Return a new action profile which is updated num_reps times.
`time_series`(ts_length[, init_actions, ...])	Return the array representing time series of action profiles.

play(init_actions=None, player_ind_seq=None, num_reps=1, random_state=None)[source]

Return a new action profile which is updated num_reps times.

Parameters:

init_actionstuple(int), optional(default=None): The action profile in the initial period. If None, selected randomly.
player_ind_seqlist(int), optional(default=None): The sequence of player indices. If None, selected randomly.
num_repsscalar(int), optional(default=1): The number of iterations.
random_stateint or np.random.RandomState/Generator, optional: Random number generator used.

Returns:

time_series(ts_length, init_actions=None, random_state=None)[source]

Return the array representing time series of action profiles.

Parameters:

ts_lengthscalar(int): The number of iterations.
init_actionstuple(int), optional(default=None): The action profile in the initial period. If None, selected randomly.
random_stateint or np.random.RandomState/Generator, optional: Random number generator used.

Returns: